We propose hardware-oriented models of intrinsic plasticity (IP) and synaptic plasticity (SP) for spiking randomly connected recursive neural network (RNN). Although the potential of RNNs for temporal data processing has been demonstrated, randomness of the network architecture often causes performance degradation. Self-organization mechanism using IP and SP can mitigate the degradation, therefore, we compile these functions in a spiking neuronal model. To implement the function of IP, a variable firing threshold is introduced to each excitatory neuron in the RNN that changes stepwise in accordance with its activity. We also define other thresholds for SP that synchronize with the firing threshold, which determine the direction of stepwise synaptic update that is executed on receiving a pre-synaptic spike. We demonstrate the effectiveness of our model through simulations of temporal data learning and anomaly detection with a spiking RNN using publicly available electrocardiograms. Considering hardware implementation, we employ discretized thresholds and synaptic weights and show that these parameters can be reduced to binary if the RNN architecture is appropriately designed. This contributes to minimization of the circuit of the neuronal system having IP and SP.

翻译：摘要：本文提出面向硬件的内在可塑性(IP)与突触可塑性(SP)模型，适用于脉冲随机连接递归神经网络(RNN)。尽管RNN在时序数据处理方面的潜力已得到验证，但网络架构的随机性常导致性能退化。基于IP与SP的自组织机制可缓解此类退化，因此我们将这些功能整合至脉冲神经元模型中。为实现IP功能，我们在RNN的每个兴奋性神经元中引入可变发放阈值，该阈值根据其活动状态呈阶梯式变化。此外，我们为SP定义了与发放阈值同步的附加阈值，这些阈值决定了在接收突触前脉冲时所执行的阶梯式突触更新方向。通过使用公开心电图数据的时序学习与异常检测仿真实验，我们验证了该模型的有效性。考虑到硬件实现，我们采用离散化阈值与突触权重，并证明在合理设计的RNN架构下，这些参数可简化为二进制形式。这有助于实现具备IP与SP功能的神经元系统电路的最小化。